Table 2 Comparison of the results of the proposed network with other networks based on the OA, FWIoU, precision, recall and F1 score.

From: Extraction of water bodies from high-resolution remote sensing imagery based on a deep semantic segmentation network

 

OA

FWIoU

Precision

Recall

F1

UNet +  + 

99.025%

93.507%

95.822%

92.772%

94.272%

SegNet

98.744%

92.877%

96.579%

89.503%

92.906%

DeepLabV3 +  + 

98.929%

94.539%

96.717%

92.989%

94.816%

WaterDeep

99.284%

95.58%

97.562%

95.486%

96.513%

Back to article page